© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 1241
    Prev
    Next
    INDEX
    Explanations

    phrases or patterns starting with "One of the" or similar structures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "one of the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.73
    heit
    -0.73
    æ³
    -0.69
    MK
    -0.69
    ENCE
    -0.68
    fulness
    -0.68
    CLE
    -0.68
    CHO
    -0.65
    lean
    -0.65
    BER
    -0.65
    POSITIVE LOGITS
     earliest
    1.03
     largest
    0.89
     aforementioned
    0.89
     finest
    0.88
     heaviest
    0.88
     busiest
    0.88
     highest
    0.86
     strongest
    0.85
     hardest
    0.83
     hottest
    0.83
    Activations Density 0.180%

    No Known Activations